{"id":"W4352976756","doi":"10.1007/978-3-031-28719-0_24","title":"Value Cores for Inner and Outer Alignment: Simulating Personality Formation via Iterated Policy Selection and Preference Learning with Self-World Modeling Active Inference Agents","year":2023,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Iterated function; Selection (genetic algorithm); Inference; Preference; Value (mathematics); Artificial intelligence; Computer science; Personality; Machine learning; Psychology; Mathematics; Statistics; Social psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002165758,0.0002452346,0.0003231417,0.001547187,0.001000849,0.001391911,0.0007282541,0.0001165409,0.000004309094],"category_scores_gemma":[0.0003981493,0.0002044799,0.00003245135,0.0007113084,0.0003285687,0.006294458,0.0009067717,0.0003805373,0.000009797568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002039104,"about_ca_system_score_gemma":0.0001926551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006730992,"about_ca_topic_score_gemma":0.0001184006,"domain_scores_codex":[0.9977628,0.00007376463,0.0009346622,0.0004081377,0.0005876723,0.0002329349],"domain_scores_gemma":[0.9966346,0.001171581,0.0006576952,0.0005470189,0.0008817078,0.0001074103],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005431455,0.00002373917,0.001362566,0.00004668068,0.00001621011,2.078269e-7,0.01408847,0.09711016,0.000006673912,0.03330194,0.00002431967,0.8539647],"study_design_scores_gemma":[0.0003394686,0.00008980078,0.001408399,0.0002181907,0.00001396925,0.00001021672,0.0001781766,0.9661185,0.000004589493,0.02899484,0.002386372,0.0002375327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2892552,0.00006285137,0.6933532,0.0008478591,0.0002288734,0.001672618,0.0001020646,0.0002343785,0.01424287],"genre_scores_gemma":[0.9768282,0.0002903705,0.02216689,0.0001997137,0.00002763819,0.0000335111,0.0000650068,0.00001198434,0.0003767174],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8690083,"threshold_uncertainty_score":0.9996448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2426187814753632,"score_gpt":0.4146930962041733,"score_spread":0.1720743147288102,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}